Automatic Speech Recognition
ONNX
Transformers.js
onnxruntime
onnxruntime-web
asr
speech-recognition
robust-asr
quantized
int4
int8
matmulnbits
gptq
on-device
browser
web
qwen3
qwen3-asr
mega-asr
Instructions to use VidraAI/mega-asr-onnx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers.js
How to use VidraAI/mega-asr-onnx with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('automatic-speech-recognition', 'VidraAI/mega-asr-onnx');
Download decoder_step_int4.onnx.data from VidraAI/mega-asr-onnx: direct link, hf CLI and curl.
- Browser
- Download file 995 MB
-
https://huggingface.co/VidraAI/mega-asr-onnx/resolve/main/decoder_step_int4.onnx.data
- Command line
-
hf download hf://VidraAI/mega-asr-onnx/decoder_step_int4.onnx.data
-
curl -L -o decoder_step_int4.onnx.data https://huggingface.co/VidraAI/mega-asr-onnx/resolve/main/decoder_step_int4.onnx.data
995 MB
- Xet hash:
- 7cb4a6da2ca0c6986564eefcfb6db30c525a819f0be6c572e869cce99fd30171
- Size of remote file:
- 995 MB
- SHA256:
- 7184b94407d9ee8bf0eb1227d20be897fb3e7da4b3fd44361b2dcb0a2ae5df38
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.